A Three-Tier Deep Learning-Based Channel Access Method for WiFi Networks

Future WiFi networks require a channel access method that provides users with high capacity. Such a method must consider 1) channel bonding, which improves the transmission capacity of Access Points (APs); and 2) spatial reuse, where APs tune their Clear Channel Assessment (CCA) threshold and transm...

Full description

Saved in:
Bibliographic Details
Main Authors: Yiwei Huang, Kwan-Wu Chin
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Transactions on Machine Learning in Communications and Networking
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10158058/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850029640279654400
author Yiwei Huang
Kwan-Wu Chin
author_facet Yiwei Huang
Kwan-Wu Chin
author_sort Yiwei Huang
collection DOAJ
description Future WiFi networks require a channel access method that provides users with high capacity. Such a method must consider 1) channel bonding, which improves the transmission capacity of Access Points (APs); and 2) spatial reuse, where APs tune their Clear Channel Assessment (CCA) threshold and transmit power in order to transmit concurrently with neighboring APs. To date, there are no solutions that <italic>jointly</italic> optimize the channels used by an AP, and the CCA threshold and transmit power of a bonded channel. To this end, we outline a three-tier deep learning approach. Briefly, at Layer-1, it selects a set of transmitting channels. At Layer-2 and Layer-3, it respectively determines the transmit power and CCA threshold for each selected channel. An AP then employs deep reinforcement learning to learn the optimal policy for each layer given its interference intensity and queue length. The simulation results show that when compared to three competing solutions, an AP that uses our approach is able to reduce its queue length by up to 62.52&#x0025; under realistic traffic load.
format Article
id doaj-art-7cc11298f3094bcbb99ff4bd801ea1ab
institution DOAJ
issn 2831-316X
language English
publishDate 2023-01-01
publisher IEEE
record_format Article
series IEEE Transactions on Machine Learning in Communications and Networking
spelling doaj-art-7cc11298f3094bcbb99ff4bd801ea1ab2025-08-20T02:59:29ZengIEEEIEEE Transactions on Machine Learning in Communications and Networking2831-316X2023-01-0119010610.1109/TMLCN.2023.328809010158058A Three-Tier Deep Learning-Based Channel Access Method for WiFi NetworksYiwei Huang0https://orcid.org/0000-0001-6556-346XKwan-Wu Chin1https://orcid.org/0000-0003-1547-9272School of Electrical, Computer and Telecommunications Engineering, University of Wollongong, Wollongong, NSW, AustraliaSchool of Electrical, Computer and Telecommunications Engineering, University of Wollongong, Wollongong, NSW, AustraliaFuture WiFi networks require a channel access method that provides users with high capacity. Such a method must consider 1) channel bonding, which improves the transmission capacity of Access Points (APs); and 2) spatial reuse, where APs tune their Clear Channel Assessment (CCA) threshold and transmit power in order to transmit concurrently with neighboring APs. To date, there are no solutions that <italic>jointly</italic> optimize the channels used by an AP, and the CCA threshold and transmit power of a bonded channel. To this end, we outline a three-tier deep learning approach. Briefly, at Layer-1, it selects a set of transmitting channels. At Layer-2 and Layer-3, it respectively determines the transmit power and CCA threshold for each selected channel. An AP then employs deep reinforcement learning to learn the optimal policy for each layer given its interference intensity and queue length. The simulation results show that when compared to three competing solutions, an AP that uses our approach is able to reduce its queue length by up to 62.52&#x0025; under realistic traffic load.https://ieeexplore.ieee.org/document/10158058/Medium accesscapacityMarkov decision processinterferencechannel aggregation
spellingShingle Yiwei Huang
Kwan-Wu Chin
A Three-Tier Deep Learning-Based Channel Access Method for WiFi Networks
IEEE Transactions on Machine Learning in Communications and Networking
Medium access
capacity
Markov decision process
interference
channel aggregation
title A Three-Tier Deep Learning-Based Channel Access Method for WiFi Networks
title_full A Three-Tier Deep Learning-Based Channel Access Method for WiFi Networks
title_fullStr A Three-Tier Deep Learning-Based Channel Access Method for WiFi Networks
title_full_unstemmed A Three-Tier Deep Learning-Based Channel Access Method for WiFi Networks
title_short A Three-Tier Deep Learning-Based Channel Access Method for WiFi Networks
title_sort three tier deep learning based channel access method for wifi networks
topic Medium access
capacity
Markov decision process
interference
channel aggregation
url https://ieeexplore.ieee.org/document/10158058/
work_keys_str_mv AT yiweihuang athreetierdeeplearningbasedchannelaccessmethodforwifinetworks
AT kwanwuchin athreetierdeeplearningbasedchannelaccessmethodforwifinetworks
AT yiweihuang threetierdeeplearningbasedchannelaccessmethodforwifinetworks
AT kwanwuchin threetierdeeplearningbasedchannelaccessmethodforwifinetworks